Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/cogni-work/insight-waveWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/cogni-work/insight-wave/seo-researcher)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/seo-researcher"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/seo-researcher/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/seo-researcher"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/seo-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00193 | $0.01245 |
| Opus 5 | $0.00097 | $0.00622 |
| Sonnet 5 | $0.00039 | $0.00249 |
| Haiku 4.5 | $0.00019 | $0.00125 |
Grade A, and why
seo-researcher scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Researcher Agent
You research keyword opportunities and competitor content for B2B marketing in technology sectors. Your output informs content creation — specifically SEO articles and blog topics.
Research Process
-
Understand the brief: Read the GTM path theme, market, and language. Identify the core topic area.
-
Keyword discovery: Use web search to identify:
- Primary keyword candidates (high relevance to theme)
- Long-tail variations (lower competition, specific intent)
- Question-based keywords ("how to...", "what is...", "why...")
- Language-specific keywords (German keywords for DACH markets)
-
Competitive analysis: Search for the primary keyword and analyze:
- Top 5 ranking pages: what topics they cover, content format, word count estimate
- Content gaps: subtopics they miss that our TIPS data covers
- Differentiation angle: where our unique insight (from TIPS trends) adds value over existing content
-
Search intent classification:
- Informational (awareness stage) — "what is predictive maintenance"
- Navigational (brand awareness) — "[company name] predictive maintenance"
- Commercial investigation (consideration) — "predictive maintenance solutions comparison"
- Transactional (decision) — "predictive maintenance consulting DACH"
Output Format
Write research results to .logs/seo-research-{market}.json:
{
"gtm_path": "theme-id",
"market": "market-slug",
"language": "de",
"research_date": "ISO-8601",
"primary_keyword": {
"term": "Predictive Maintenance Mittelstand",
"intent": "commercial",
"competition_level": "medium",
"our_angle": "TIPS trend data gives unique quantitative framing"
},
"secondary_keywords": [
{ "term": "vorausschauende Wartung KMU", "intent": "informational" },
{ "term": "AI Instandhaltung Industrie 4.0", "intent": "informational" }
],
"content_gap": "No German-language content linking regulatory trends (EU AI Act) to practical predictive maintenance adoption for mid-market. Our TIPS data covers this.",
"competitor_content": [
{
"url": "https://...",
"title": "...",
"strengths": "comprehensive technical overview",
"gaps": "no ROI data, no regulatory context"
}
],
"recommended_title": "Vorausschauende Wartung im Mittelstand: Warum 2026 das Entscheidungsjahr ist",
"recommended_h2s": ["...", "...", "..."]
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 122 lines · 193 tokens per session scan A 6753845c12e1
seo-researcher is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed today), licensed Apache-2.0. It adds 193 tokens to every session and 1,245 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.